{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:XGD3IUQ5TGNDT6OIWVEORBR32S","short_pith_number":"pith:XGD3IUQ5","schema_version":"1.0","canonical_sha256":"b987b4521d999a39f9c8b548e8863bd4ac867ee097d3fcd102cf7e5f4ab03f2b","source":{"kind":"arxiv","id":"2501.16385","version":2},"attestation_state":"computed","paper":{"title":"FBQuant: FeedBack Quantization for Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.LG","authors_text":"Hengyu Fang, Li Du, Liulu He, Rongyu Zhang, Yichuan Bai, Yijiang Liu, Yuan Du","submitted_at":"2025-01-25T06:04:07Z","abstract_excerpt":"Deploying Large Language Models (LLMs) on edge devices is increasingly important, as it eliminates reliance on network connections, reduces expensive API calls, and enhances user privacy. However, on-device deployment is challenging due to the limited computational resources of edge devices. In particular, the key bottleneck stems from memory bandwidth constraints related to weight loading. Weight-only quantization effectively reduces memory access, yet often induces significant accuracy degradation. Recent efforts to incorporate sub-branches have shown promise for mitigating quantization erro"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2501.16385","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-01-25T06:04:07Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"fee68ca335eca958fed84073edb8fc36146f386450b50e8a79aa6f949cbba064","abstract_canon_sha256":"a61e25f31c8a9ed924df53d3e0139d60f6e48fac2176237bdfa90fb7a8c9383d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:08:15.514703Z","signature_b64":"iVXzxSPVurYkluDCymi7CfLYgnrF6UGdHpcT+u29tDMMXkOURiJVUR/OOZ+s5ZpbIVI4JIx2xZzIxi+qN423CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b987b4521d999a39f9c8b548e8863bd4ac867ee097d3fcd102cf7e5f4ab03f2b","last_reissued_at":"2026-07-05T11:08:15.514191Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:08:15.514191Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"FBQuant: FeedBack Quantization for Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.LG","authors_text":"Hengyu Fang, Li Du, Liulu He, Rongyu Zhang, Yichuan Bai, Yijiang Liu, Yuan Du","submitted_at":"2025-01-25T06:04:07Z","abstract_excerpt":"Deploying Large Language Models (LLMs) on edge devices is increasingly important, as it eliminates reliance on network connections, reduces expensive API calls, and enhances user privacy. However, on-device deployment is challenging due to the limited computational resources of edge devices. In particular, the key bottleneck stems from memory bandwidth constraints related to weight loading. Weight-only quantization effectively reduces memory access, yet often induces significant accuracy degradation. Recent efforts to incorporate sub-branches have shown promise for mitigating quantization erro"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.16385","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2501.16385/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2501.16385","created_at":"2026-07-05T11:08:15.514251+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.16385v2","created_at":"2026-07-05T11:08:15.514251+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.16385","created_at":"2026-07-05T11:08:15.514251+00:00"},{"alias_kind":"pith_short_12","alias_value":"XGD3IUQ5TGND","created_at":"2026-07-05T11:08:15.514251+00:00"},{"alias_kind":"pith_short_16","alias_value":"XGD3IUQ5TGNDT6OI","created_at":"2026-07-05T11:08:15.514251+00:00"},{"alias_kind":"pith_short_8","alias_value":"XGD3IUQ5","created_at":"2026-07-05T11:08:15.514251+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.15689","citing_title":"BASE-Q: Bias and Asymmetric Scaling Enhanced Rotational Quantization for Large Language Models","ref_index":9,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XGD3IUQ5TGNDT6OIWVEORBR32S","json":"https://pith.science/pith/XGD3IUQ5TGNDT6OIWVEORBR32S.json","graph_json":"https://pith.science/api/pith-number/XGD3IUQ5TGNDT6OIWVEORBR32S/graph.json","events_json":"https://pith.science/api/pith-number/XGD3IUQ5TGNDT6OIWVEORBR32S/events.json","paper":"https://pith.science/paper/XGD3IUQ5"},"agent_actions":{"view_html":"https://pith.science/pith/XGD3IUQ5TGNDT6OIWVEORBR32S","download_json":"https://pith.science/pith/XGD3IUQ5TGNDT6OIWVEORBR32S.json","view_paper":"https://pith.science/paper/XGD3IUQ5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.16385&json=true","fetch_graph":"https://pith.science/api/pith-number/XGD3IUQ5TGNDT6OIWVEORBR32S/graph.json","fetch_events":"https://pith.science/api/pith-number/XGD3IUQ5TGNDT6OIWVEORBR32S/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XGD3IUQ5TGNDT6OIWVEORBR32S/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XGD3IUQ5TGNDT6OIWVEORBR32S/action/storage_attestation","attest_author":"https://pith.science/pith/XGD3IUQ5TGNDT6OIWVEORBR32S/action/author_attestation","sign_citation":"https://pith.science/pith/XGD3IUQ5TGNDT6OIWVEORBR32S/action/citation_signature","submit_replication":"https://pith.science/pith/XGD3IUQ5TGNDT6OIWVEORBR32S/action/replication_record"}},"created_at":"2026-07-05T11:08:15.514251+00:00","updated_at":"2026-07-05T11:08:15.514251+00:00"}